alphafold-database

Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/alphafold-database/SKILL.md

Quality

Content

65%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with extensive executable examples, but it is held back by content duplication, an off-mission promotional section, capability-oriented rather than workflow-oriented sequencing, and a monolithic structure that underuses the available reference file.

Suggestions

De-duplicate the pLDDT/PAE threshold tables (keep one canonical 'Confidence Interpretation Guidelines' section) and remove the K-Dense Web promotional section, which does not serve the skill's function.

Move the bulk of the API/code examples and the use-case catalogs into references/api_reference.md, leaving SKILL.md as a lean overview with well-signaled links.

Add explicit validation checkpoints to the batch/bulk-download workflow (e.g. verify file count and integrity after gsutil cp, retry on partial downloads) to lift workflow clarity above the batch cap.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but pLDDT/PAE threshold tables are duplicated (section 3 inline comments and 'Confidence Interpretation Guidelines'), the AlphaFold ID format is explained twice, 'When to Use' overlaps 'Common Use Cases', and the K-Dense Web promotional section is off-mission padding.	3 / 5
Actionability	Abundant copy-paste-ready, executable code spanning Biopython, REST requests, gsutil, BigQuery, subprocess, and structure parsing, with concrete URLs and identifiers covering the common cases.	5 / 5
Workflow Clarity	Content is organized by capability (six numbered sections) rather than as a sequenced workflow, and explicit validation checkpoints/feedback loops are largely absent; the bulk-download batch path does include integer validation and try/except, but no 'verify download succeeded' step, so it sits at the cap for batch operations.	3 / 5
Progressive Disclosure	A single reference (api_reference.md) is clearly signaled one level deep in a dedicated Resources section, but the 512-line SKILL.md body keeps most API examples, use-case catalogs, and threshold guidance inline rather than splitting them out, leaving structure only moderately organized.	3 / 5
	Total	14 / 20 Passed

Description

66%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and well-targeted to a distinct niche with good trigger keywords, but it omits an explicit 'Use when...' trigger clause, which caps its completeness score. Adding concrete trigger guidance would lift the completeness and trigger-term dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks about AlphaFold predictions, needs a protein structure by UniProt ID, or wants pLDDT/PAE confidence analysis.'

Add common natural synonyms and file extensions (e.g. 'predicted structures', '.cif', '.pdb', 'confidence scores') to broaden trigger-term coverage.

Tighten the closing 'for drug discovery and structural biology' into specific use-case triggers rather than broad domain labels.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE)') with comprehensive domain coverage; not a 5 because coverage is three actions rather than a broader enumeration.	4 / 5
Completeness	Has a clear 'what' ('Access AlphaFold 200M+ AI-predicted protein structures') but no explicit 'Use when...' trigger clause; the trailing 'for drug discovery and structural biology' is only a weakly implied 'when', capping completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Good keyword coverage including natural domain terms ('protein structures', 'UniProt ID', 'PDB/mmCIF', 'drug discovery'); a few natural synonyms or file extensions (e.g. '.cif', 'predicted structure') are missing.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (AlphaFold predicted structures, UniProt ID lookups) with distinct triggers and minimal overlap; not a 5 because the broad 'drug discovery and structural biology' framing could marginally overlap with general structural-biology skills.	4 / 5
	Total	15 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (513 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

Repository: googolme/run0204
Path: scientific-skills/alphafold-database/SKILL.md
Commit: 4902409

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.